story-to-plan-orchestrator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted 'product intent' and authorized referenced inputs, which establishes an ingestion surface for indirect prompt injection. The skill includes defensive instructions to preserve access gaps and avoid reconstructing missing context when external sources are inaccessible.
- [SAFE]: The skill acts as an orchestrator and process overlay, directing tasks to other component skills rather than executing low-level shell commands or network operations directly.
- [SAFE]: No indicators of credential exfiltration, persistence, or code obfuscation were found in the skill or its reference files.
Audit Metadata